Round 1

Reviewer 1 Report

Please see the attached file.

Comments for author File: Comments.pdf

Author Response

1. In abstract, it is suggested to avoid using long sentence, such as “In view of the  problem … lower energy efficiency”, which would affect the readability of this paper.

Response:

The long sentence in the abstract is revised as several short sentences，as shown in line 11 to line 14.

 

2. The background is not well introduced. For the second paragraph, the authors have not introduced what is the technical core and reasons of advantages of CA. The authors only claimed that CA can improve capacity and reduce interference instead of why.

Response:

For the second paragraph we added introduction what is the technical core and reasons of advantages of CA. The revised contents are shown in line 58 to line 64.

 

3. It is suggested to use past tence to introduce the existing works, such as [18] and [22].

Response:

We had used past tence to introduce the existing works, as shown in line 70, line 76, line 93, line 95, line 110, line 112, line 113, line 118, line 122.

 

4. Except for CA, some other recent techniques and schemes, such as RIS [R1],  secure EE [R2], NOMA [R3] and RSMA [R4] should be introduced to highlight the state-of-the-art of this paper.  [R1] “Refracting RIS aided hybrid satellite-terrestrial relay networks: Joint beamforming design  and optimization,” IEEE Transactions on Aerospace and Electronic Systems, vol. 58, no. 4, pp.  3717-3724, Aug. 2022.

[R2] “SLNR-based secure energy efficient beamforming in multibeam satellite systems,” IEEE Transactions on Aerospace and Electronic Systems, early access, Jul. 2022, doi:  10.1109/TAES.2022.3190238.

[R3] “Joint beamforming and power allocation for satellite-terrestrial integrated networks with non-orthogonal multiple access,” IEEE Journal of Selected Topics in Signal Processing, vol. 13,  no. 3, pp. 657-670, June 2019.

[R4] “Supporting IoT with rate-splitting multiple access in satellite and aerial-integrated networks,” IEEE Internet of Things Journal, vol. 8, no. 14, pp. 11123-11134, Jul. 2021.

Response:

We have added the recent techniques and schemes introduced to highlight the state-of-the-art of this paper. The related literatures include references [R1],[R2],[R3] and[R4] pointed out by the review experts. The revised contents are shown in line 73 to line 75, line 772 to line 775, line 782 to line 783 and line 786 to line 787.

 

5. 5. Both the motivations and contributions are missing, which should be clarified to emphasize the novelty of this paper.

Response:

At the end of the introduction, the motivations and contributions are added. The added contents are shown in line 124 to line 169.

 

6. The authors should carefully check the whole paper to avoid writing and grammar  errors. For instance, 1) “In [17] studied the energy-efficient resource”; 2) “The optimal joint CC selection and RB allocation methods performed disjoint schemes due to comprehensive view”;3) “In [22], propose QoS-aware”; 4)

Response:

We have checked and corrected the writing and grammar errors, as shown in line 70, line 76, line 88, line 93, line 118 , line 122,line 519,line 520.

 

7. 7. There are too many symbols in this paper, it is suggested to add a Table to list them.

Response:

We have added List of main symbols to list main symbols and related definition, see Appendix 1, as shown in line 853 to 855.

Reviewer 2 Report

 

Review: CA Energy Saving and Sustainable Joint Resource Optimization Scheme Based on 5G Channel Information Prediction of Machine Learning

 

 

1. Results: Recommend to be Major revisions     

This paper proposes CA energy-efficient sustainable joint resource optimization allocation scheme (PEJA scheme) based on channel information prediction. Firstly, the algorithm of random forest predicting channel state information is designed. On the basis, the CA energy-efficient joint resource optimization allocation scheme (PEJA scheme) based on channel information prediction is proposed. The proposed PEJA is verified by simulation experiments. Compared with NP-EJA, ERAA, EGA and GA algorithms, it achieves better energy-efficient performance under different user numbers and different maximum transmit powers, the throughput performance is also higher than that of the comparison algorithm; The PEJA algorithm has higher energy-efficient than the PEJA-NC algorithm which does not consider CC handover of narrowband users. To sum up, the proposed PEJA energy-efficient resource allocation scheme maximizes system energy efficiency and achieves higher throughput.

This paper is with none merits for Sustainability, it could be accepted after re-submission.  

Firstly, the abstract should be refined to clearly indicate what authors had done within 200 words.

Secondly, for Section 1, authors should provide the comments of the cited papers after introducing each relevant work. What readers require is, by convinced literature review, to understand the clear thinking/consideration why the proposed approach can reach more convinced results. This is the very contribution from authors. In addition, authors also should provide more sufficient critical literature review to indicate the drawbacks of existed approaches, then, well define the main stream of research direction, how did those previous studies perform? Employ which methodologies? Which problem still requires to be solved? Why is the proposed approach suitable to be used to solve the critical problem? We need more convinced literature reviews to indicate clearly the state-of-the-art development. And very importantly, authors always have to write a paragraph saying: “The rest of the paper is organized as follows. Section 2 contains the literature review. Section 3 contains the methodology (method). Section 4 contains the results. Section 5 contains the conclusions and policy implications”. So, the reader knows what’s coming next.

For Sections 2 to 4, authors should also introduce their proposed research framework more effective, i.e., some essential brief explanation vis-à-vis the text with a total research flowchart or framework diagram for each proposed algorithm to indicate how these employed models are working to receive the experimental results. It is difficult to understand how the proposed approaches are working.

For Section 5, authors should use more alternative models as the benchmarking models, authors should also conduct some statistical test to ensure the superiority of the proposed approach, i.e., how could authors ensure that their results are superior to others? Meanwhile, authors also have to provide some insight discussion of the results.

 

 

 

 

 

 

 

 

 

 

Author Response

1: This paper is with none merits for Sustainability, it could be accepted after re-submission.

Response: For sustainability, it mainly refers to the energy saving resource allocation scheme designed by us, which can improve the energy efficiency, thus achieving the purpose of energy conservation, so we call it sustainable. If the review finds that is inappropriate, we have modified the title and abstract to delete sustainability. Paper title is modified as ” CA Energy Saving Joint Resource Optimization Scheme Based on 5G Channel Information Prediction of Machine Learning”, as shown in line 2.

 

2: Firstly, the abstract should be refined to clearly indicate what authors had done within 200 words.

Response:

We simplified the abstract to less than 200 words, and revised it more clearly to express the main work of the paper. The revised contents are shown in line 11 to line 16 and line 18 to line 21.

 

3: Secondly, for Section 1, authors should provide the comments of the cited papers after introducing each relevant work. What readers require is, by convinced literature review, to understand the clear thinking/consideration why the proposed approach can reach more convinced results. This is the very contribution from authors. In addition, authors also should provide more sufficient critical literature review to indicate the drawbacks of existed approaches, then, well define the main stream of research direction, how did those previous studies perform? Employ which methodologies? Which problem still requires to be solved? Why is the proposed approach suitable to be used to solve the critical problem? We need more convinced literature reviews to indicate clearly the state-of-the-art development. And very importantly, authors always have to write a paragraph saying: “The rest of the paper is organized as follows. Section 2 contains the literature review. Section 3 contains the methodology (method). Section 4 contains the results. Section 5 contains the conclusions and policy implications”. So, the reader knows what’s coming next.

Response: 

We have revised the literature review and point out the shortcomings of the existing research work (line 124 to line 134). At the end of the introduction, we supplement the writing motivation  (line 124 to line 134)and contribution of the paper (line 135 to line 169), and add the organization and structure of the paper (line 170 to line 174).

4: For Sections 2 to 4, authors should also introduce their proposed research framework more effective, i.e., some essential brief explanation vis-à-vis the text with a total research flowchart or framework diagram for each proposed algorithm to indicate how these employed models are working to receive the experimental results. It is difficult to understand how the proposed approaches are working.

Response:

For Sections 2 to 4, the flowchart of algorithm 1 (random forest prediction) is added in paper, that is seen in Fig.1 (line 345 to line 352).

The flowchart of algorithm 4 (DDJBNBC) is added in paper, that is seen in Fig.2(line 540 to line 541, line 568 to line 571). Due to the simplicity of algorithms 2,3 and the limitation of layout, we omit the algorithm flow chart.

The flow chart of the PEJA (algorithm 5) is added in paper, it can be seen in Fig.3(line 587 to line 603). The relationship between algorithm 5 and algorithms 1, 3 ,4 is explained (line 582 to line 586).

 

 

5: For Section 5, authors should use more alternative models as the benchmarking models, authors should also conduct some statistical test to ensure the superiority of the proposed approach, i.e., how could authors ensure that their results are superior to others? Meanwhile, authors also have to provide some insight discussion of the results.

Response:

It's so regret that we can't find more benchmark models. But we have done some statistical test to ensure the superiority of the proposed approach, For example, Fig.8 shows the cumulative distribution functions of average normalized energy efficiency (EE) of different algorithms. Not only that, we have added the cumulative distribution function statistical results with EE varying in the case of (, ), shown in Fig.9 (line 708 to line 715).  we also provide some explanations (line 697 to line 699) and some discussion of the results (line 716 to line 725).

Round 2

Reviewer 1 Report

The authors have addressed my concerns, no further comments.

Reviewer 2 Report

Authors have completely addressed all my concerns.